Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3084. Min Range: -6.3084
Max Act: 6.3084. Min Act: -0.1700
Data Index: 445914 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3084. Min Range: -6.3084
Max Act: 6.1521. Min Act: -0.1700
Data Index: 8706304 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.8084. Min Act: -0.1700
Data Index: 1306464 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.8396. Min Act: -0.1700
Data Index: 5704130 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.8084. Min Act: -0.1700
Data Index: 1513457 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.7459. Min Act: -0.1700
Data Index: 8177439 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.7771. Min Act: -0.1700
Data Index: 3230144 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6518745 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.7146. Min Act: -0.1700
Data Index: 6604570 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6202772 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6834. Min Act: -0.1700
Data Index: 7572827 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.7146. Min Act: -0.1700
Data Index: 3059389 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6834. Min Act: -0.1700
Data Index: 5340432 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6521. Min Act: -0.1700
Data Index: 5404281 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6209. Min Act: -0.1700
Data Index: 1260439 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6834. Min Act: -0.1700
Data Index: 605012 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6209. Min Act: -0.1700
Data Index: 5426109 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.6209. Min Act: -0.1700
Data Index: 2155752 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.5896. Min Act: -0.1700
Data Index: 7051157 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3084. Min Range: -6.3084
Max Act: 5.5896. Min Act: -0.1698
Data Index: 8749497 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19